# Best embedding and reranking APIs for AI agents (slim)

> Amazon Nova Multimodal Embeddings (BB), OpenAI embeddings (BB) and Cohere Embed and Rerank (BB) lead the 10 ranked embedding and reranking APIs. Picks by need, strengths, weaknesses and prices from the Anchor benchmark.

- Full: https://www.anchorterminal.com/best/embeddings/index.md (~5,700 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/best/embeddings/index.json · canonical https://www.anchorterminal.com/best/embeddings/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-08

All 10 ranked embedding and reranking APIs on the Anchor benchmark, with a pick for each need and where each one falls short. Scores come from public evidence, re-checked as vendors change.

- Ranked: 10 · agent-ready (BB or better): 4 · accept x402: 0 · hosted endpoints: 9
- Full ranked table: https://www.anchorterminal.com/categories/embeddings.md
- Head-to-head comparisons: https://www.anchorterminal.com/compare/embeddings/index.md (45)
- Methodology: https://www.anchorterminal.com/benchmark/index.md

## The shortlist

| # | Tool | Grade | Score | Best for | Price | Where |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [Amazon Nova Multimodal Embeddings](https://www.anchorterminal.com/tools/amazon-nova-embeddings.md) | BB | 75 | Suited to mixed-media retrieval for teams already on AWS, especially video and audio archives processed through S3. | Pay per use | hosted |
| 2 | [OpenAI embeddings](https://www.anchorterminal.com/tools/openai-embeddings.md) | BB | 73.2 | An agent already on OpenAI that needs cheap general-purpose text retrieval with a small index. | Pay per use | hosted |
| 3 | [Cohere Embed and Rerank](https://www.anchorterminal.com/tools/cohere-embed.md) | BB | 72.5 | Best when reranking is the job, or for long multilingual documents and image-heavy material where a 128K embedding context helps, with a cheaper Fast model for queries against a Pro index. | $2 / 1k req | hosted |
| 4 | [Gemini Embedding](https://www.anchorterminal.com/tools/gemini-embedding.md) | BB | 70.6 | Multimodal corpora, especially video and audio, and for agents already on Google Cloud. | Freemium | hosted |
| 5 | [Jina Embeddings and Reranker](https://www.anchorterminal.com/tools/jina-embeddings.md) | C | 61 | Reranking large candidate sets and multimodal corpora with audio or video. | Freemium | hosted |
| 6 | [NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/tools/nvidia-nemo-retriever.md) | C | 61 | Teams that already run NVIDIA GPUs and need embedding and reranking inside their own network, including page-image retrieval with the VL models. | Freemium | local |
| 7 | [Voyage AI embeddings and rerankers](https://www.anchorterminal.com/tools/voyage-ai.md) | C | 58.8 | Retrieval quality across domains, code and long documents, with a reranker from the same key. | Freemium | hosted |
| 8 | [Mistral Embed and Codestral Embed](https://www.anchorterminal.com/tools/mistral-embeddings.md) | C | 57.9 | EU data residency, Mistral-only stacks and code retrieval with small vectors. | Freemium | hosted |
| 9 | [Nomic Embed](https://www.anchorterminal.com/tools/nomic-embed.md) | D | 49.2 | Teams that want a hosted endpoint for an open-weight model they can also run themselves, with the same vectors either way. | Freemium | hosted |
| 10 | [ZeroEntropy zerank and zembed](https://www.anchorterminal.com/tools/zeroentropy.md) | F | 13.7 | Only as open weights for teams that can self-host a reranker or embedding model. | Pay per use | hosted |

## Picks by need

- Highest score overall: [Amazon Nova Multimodal Embeddings](https://www.anchorterminal.com/tools/amazon-nova-embeddings.md), BB, 75/100 on the benchmark. Also [OpenAI embeddings](https://www.anchorterminal.com/tools/openai-embeddings.md), BB, 73.2/100.
- Schema & documentation: [Cohere Embed and Rerank](https://www.anchorterminal.com/tools/cohere-embed.md), 92/100 on schema & documentation, against 76 for the overall leader.
- Agent ergonomics: [Voyage AI embeddings and rerankers](https://www.anchorterminal.com/tools/voyage-ai.md), 98/100 on agent ergonomics, against 78 for the overall leader.
- Security & auth: [OpenAI embeddings](https://www.anchorterminal.com/tools/openai-embeddings.md), 95/100 on security & auth, against 91 for the overall leader.
- Maintenance & community: [Cohere Embed and Rerank](https://www.anchorterminal.com/tools/cohere-embed.md), 90/100 on maintenance & community, against 50 for the overall leader.
- Transparency & trust: [OpenAI embeddings](https://www.anchorterminal.com/tools/openai-embeddings.md), 85/100 on transparency & trust, against 79 for the overall leader.
- A hosted MCP endpoint: [Jina Embeddings and Reranker](https://www.anchorterminal.com/tools/jina-embeddings.md), remote MCP server, nothing to install.
- Self-hosting under an open licence: [NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/tools/nvidia-nemo-retriever.md), self-hosted, Proprietary containers under the NVIDIA Software Licence Agreement and Product-Specific Terms for AI Products licence.

## How to choose

- Vector dimensions and size: Check the vector dimensions and whether they can be shortened, because the index stores and scans every dimension for every query.
- Query and document purposes: Check whether queries and documents can be embedded with different purpose settings, since the setting can change which results rank highest.
- Languages and input types: Confirm which languages and modalities the model supports, including images and code, because retrieval quality can fall outside those.
- Maximum input length: Check the maximum input length and whether long documents are segmented for you, because a truncated chunk silently loses the text that answers a query.

- How the benchmark tests this category: The same corpus and queries embedded with each model, then the top results reranked. We check retrieval quality against labelled answers, latency and the cost per million tokens.

Each listing's verdict, strengths and weaknesses: https://www.anchorterminal.com/best/embeddings/index.md